Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks

Haotong Liu; Congzhao Ma; Hongyan Tian

doi:doi:10.11648/j.sr.20261406.17

Research Article |

| Peer-Reviewed

Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks

Haotong Liu^*, Congzhao Ma, Hongyan Tian

Published in Science Research (Volume 14, Issue 6)

Received: 10 September 2026 Accepted: 22 October 2026 Published: 10 November 2026

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

To address prominent problems in the traditional operation and maintenance of crude oil tank farms, including delayed response of environmental control, low efficiency of fault troubleshooting and insufficient accuracy of pollutant monitoring, this paper constructs an overall framework for intelligent environmental operation and maintenance of crude oil tank farms based on the Internet of Things, edge computing and big data. A terminal-edge-cloud collaborative integrated platform for data acquisition and analysis is established to integrate multi-source monitoring data such as VOCs emissions, site water quality and equipment operating conditions. Combined with data modeling and intelligent algorithms, it realizes accurate traceability of pollution sources, early warning of equipment faults and optimization of operation workflows. Engineering tests prove that the system improves the recognition accuracy of environmental anomalies and operation efficiency, reduces hydrocarbon emissions and energy consumption, and provides technical support for the green, low-carbon, safe and efficient management of petrochemical crude oil tank farms.

Published in	Science Research (Volume 14, Issue 6)
DOI	10.11648/j.sr.20261406.17
Page(s)	439-444
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2026. Published by Science Publishing Group

Keywords

Big Data, Crude Oil Tank Area, Intelligent operation and maintenance，Environmental monitoring

1．引言

原油罐区作为石油化工储运系统的核心单元，在常态化运行过程中，极易出现VOCs挥发扩散、含油污水渗漏、设备尾气排放超标等各类环保隐患，始终是石化行业生态环保与安全生产管控的重点场景。现阶段行业普遍采用的人工巡检、周期性维保等传统运维方式，存在监测覆盖不全、数据更新滞后、问题处置被动等诸多短板，已然无法适配当前日趋严格的环保排放标准与安全生产管控要求

[4]

。大数据信息技术的成熟与普及，为原油罐区环保运维的智能化转型提供了全新的技术路径

[13, 16]

；通过全域运行数据的实时采集、多维度数据的深度挖掘分析、运行状态的智能研判，可从根源上破解传统运维模式的诸多弊端，全面提升罐区污染防控的精细化管理水平，助力石化储运行业实现绿色、安全、高质量发展

[1]

。

2．原油罐区传统环保运维现状及痛点

2.1．运维模式整体滞后

目前，国内大部分原油罐区依旧沿用人工巡检、定期检修、事后整改的传统运维管理模式；日常巡检固定为每日两次，重点设备常态化检修频次为每周一次，整体环保隐患的排查与处置工作，完全依托运维人员的实操经验推进。该运维模式存在较强的被动性与随机性，无法完成全天候、不间断的动态监测工作，针对储罐呼吸阀微渗漏、管线轻微泄漏、低浓度VOCs无组织逸散等隐蔽性较强的环保隐患，难以做到早发现、早干预、早处置。结合石化行业罐区运维调研统计情况来看，传统运维体系下，罐区多数轻微环保隐患难以在萌芽阶段被精准识别，隐患持续累积后逐步发展为超标排放问题，进一步加大了罐区环保管控的难度与安全风险

[3, 8, 15]

。

2.2．监测数据碎片化严重

原油罐区环保运维工作，涵盖VOCs浓度、罐区水质、设备温压参数、土壤油气含量、废气回收设备运行工况等多项监测维度；但现阶段罐区各类监测设备多为独立布设、单独运行，设备数据接口标准不统一、数据存储格式差异显著，进而形成大量相互割裂的数据孤岛。常规监测数据的采集间隔控制在十至三十分钟区间，数据更新存在明显滞后性，同时缺少多源数据联动融合、综合分析的技术机制，仅依靠单一维度监测数据，无法精准追溯污染产生原因与设备故障核心根源

[14]

。

Download: Download full-size image

Figure 1. 图1 传统原油罐区环保数据监测架构示意图。

2.3．环保运维成本偏高、管控精度不足

传统罐区环保运维模式依赖大量人力值守、设备配套及耗材物料支撑；对于中型原油罐区而言，每年投入的人工巡检、设备维保以及污染问题整改的综合成本居高不下，整体运维开支体量较大。传统人工监测模式存在天然精度短板，常规气体传感监测设备稳定性不足、判识偏差明显，极易引发运维管控失衡问题；要么出现冗余的过度运维，造成资源浪费，要么产生运维盲区、遗漏潜在安全环保隐患。在污染管控层面，传统管控体系存在明显滞后性，仅能在污染物超标问题发生后开展事后整改；无法提前研判污染演变趋势与风险走向，难以适配当前石化行业VOCs减量管控、污水稳定达标排放的精细化治理标准，极大制约了石化罐区的绿色低碳转型发展。

3．大数据赋能罐区环保智能运维核心架构

3.1．整体架构设计

本次设计结合原油罐区日常运维场景的实际特点，贴合现场环保管控的规范要求，搭建起“端感知-边计算-云分析”三级联动的大数据智能运维整体架构。方案深度融合物联网感知、边缘算力调度、大数据建模、智能预警研判四项核心技术，落地罐区环保运维全流程智能化管控体系。整套架构贯穿数据采集归集、数据规范治理、智能研判分析、风险预警处置、运维策略优化全业务链条，可有效破解传统罐区运维模式下数据零散割裂、监测存在滞后性、问题处置被动滞后等行业痛点；整体架构的可视化效果如图2所示

[2]

。

Download: Download full-size image

Figure 2. 图2 整体架构的可视化效果。

3.2．感知层：全域多源数据精准采集

感知层是整套系统的核心数据基底，依托罐区全域布设的高精度智能感知设备，全面覆盖原油罐区环保监测参数、设备运行工况的全维度数据采集工作。为满足罐区VOCs排放的精细化监测需求，项目在储罐顶部、呼吸阀周边、罐区边界等关键监测点位，布设二十八组高精度气体传感设备；设备监测量程可达0-1000 mg/m³，支持每秒一次的高频数据采集，保障废气排放数据的实时捕捉

[5]

。针对含油污水监测场景，我们在罐区排水口、沉淀池等核心区域，配套安装八套在线水质监测装置，可动态采集水体COD、石油类物质、悬浮物等关键指标的实时变化数据。同时，现场同步布设温度、压力、液位、振动四类传感设备共计四十六套，全方位采集储罐本体及配套附属设备的运行状态信息。相较于传统人工采集与简易设备监测模式，本系统有效提升了现场数据的采集密度，全面消除罐区监测盲区，真正实现罐区整体运行状态的无死角、动态化监测。

3.3．边缘层：实时数据预处理与快速响应

罐区现场部署专属边缘计算节点，主要承担终端设备海量实时数据的就地处理工作；通过完成数据清洗、筛选核验、标准化规整等前置处理流程，剔除环境干扰、设备工况波动引发的异常无效数据，从源头减少云端数据传输量，降低平台整体运行负荷。系统搭载卡尔曼滤波算法开展监测数据降噪优化，能够精准修正传感器采集数据的偏差问题，显著提升现场监测数据的真实性与精准度。除此之外，边缘计算节点内置本地化预警研判机制，可自主识别介质泄漏、参数超标、设备运行异常等各类紧急工况，达成毫秒级的本地预警联动效果；无需依托云端调度指令，便可自主完成现场初步应急处置响应，彻底弥补传统运维系统依赖远程调度、响应滞后的行业短板。

3.4．云层：大数据建模与智能运维分析

云端搭建分布式大数据存储与智能分析一体化平台，归集边缘层上传的标准化合规数据，搭建专属原油罐区环保运维数据库。数据库涵盖设备实时工况、历史故障台账、环保排放台账、日常运维记录四大核心数据板块，为智能分析建模提供完整数据支撑。平台引入CNN卷积神经网络深度学习算法，完成多维度、多来源数据的融合研判，针对性构建污染溯源分析、设备寿命预判、运维策略优化三大核心智能模型。依托整套云端分析体系，罐区运维管理模式实现全面升级，彻底摆脱传统事后整改的被动模式，形成事前风险预判、事中动态管控的智能化运维新格局。

4．大数据智能运维核心技术应用与效果

4.1．多源数据融合治理技术

针对传统罐区数据碎片化问题，采用标准化数据治理技术，统一各类监测设备的数据接口与传输协议，对异构数据进行格式转换、关联匹配、分类归档。通过数据关联算法，建立设备工况与环保排放的联动关系，例如关联储罐呼吸阀运行状态与VOCs排放浓度、关联管线压力波动与污水渗漏情况。数据治理后，罐区数据有效利用率从32%提升至89%，为智能分析提供精准数据支撑

[10]

。

表1 不同阶段数据利用率对比。

运维模式	数据采集密度	数据有效利用率	数据误差率
传统人工运维模式	10-30分钟/次	32%	12.0%
大数据智能运维模式	1秒/次	89%	2.1%

4.2．环保异常智能预警与溯源技术

依托大数据智能分析模型，罐区可实现各类环保异常的精准预警，同时快速完成问题溯源与点位定位

[11]

。模型基于海量历史故障案例、常态化污染物排放数据完成训练搭建，能够精准识别微小泄漏、异常挥发等隐蔽性较强的环保隐患

[6]

。同时可精准区分设备故障、环境干扰、人工操作偏差等各类诱因造成的工况异常，从根源降低预警误判、漏判问题的发生概率。经现场落地应用验证，该预警体系可精准识别VOCs超标、污水渗漏、设备密封失效等常见环保问题，检测判定工况稳定。对比传统管控模式，系统异常识别精度、问题溯源处置效率提升显著，彻底改善了传统排查方式滞后、判定不准的行业短板。整套体系支持全天候不间断在线监测，实时采集罐区各监测点位的排放数据并同步分析研判，可提前预判潜在环保风险。依托可视化溯源功能，能够快速锁定问题位置、诱发原因及影响范围，为现场人员快速处置、闭环整改提供详实的数据支撑，有效防范各类环保事故滋生

[7]

。

4.3．设备智能运维与寿命预判技术

依托大数据时序分析核心算法，系统持续采集储罐、呼吸阀、油气回收装置、污水处理设备等核心环保设施的全维度运行参数，深度挖掘设备长期运行过程中的性能衰减规律，精准预判故障爆发周期与设备剩余服役时长

[12]

。结合各类设备的实时运行工况，系统可智能生成差异化检修运维方案，摒弃传统固定周期检修的粗放管理模式，真正落实按需维保、精准运维的智能化管控思路。该技术落地应用后，有效减少了罐区设备故障停机次数，延长了设备整体使用年限，缩减了年度运维成本，从设备运行端规避了故障诱发的各类环境污染问题。系统可自动归集设备运行台账、检修记录及损耗数据，搭建完整的设备全生命周期数字化档案，提前预警零部件老化、性能衰减等潜在问题。有效规避过度检修、漏检失修等管理漏洞，全面提升罐区环保设备运行的稳定性与安全可靠性。

4.4．环保能耗智能优化技术

大数据管控系统统筹整合罐区油气回收、污水处理、通风降温等环保设备的运行能耗、工况参数与治理效能数据，动态迭代优化设备运行参数，科学调整设备启停及运行调度策略。系统以污染物达标排放为核心底线，灵活适配现场复杂多变的生产工况。在污染负荷偏低时段，自主下调设备运行功率以降低能耗；在污染物浓度攀升时段，主动强化设备治理能力，保障排放合规，实现环保治理与节能降耗的双向统筹、协同优化。结合长期现场应用效果来看，该优化技术可有效降低罐区环保设备综合能耗，减少年度VOCs总排放量，全面提升罐区环保治理的整体效能与经济效益。系统具备多设备联动调控能力，可结合罐区环境监测数据、生产运行工况综合分析，实时优化能耗配比结构，杜绝设备无效高负荷运转，为罐区构建绿色低碳、合规高效的智能环保管控体系提供有力支撑。

5．技术应用成效综合分析

选取某中型原油罐区（12座10万m³储罐）开展为期1年的试点应用，从环保管控、运维效率、成本控制三个维度开展成效分析，全面验证大数据智能运维技术的应用价值。试点应用前后核心指标对比见表2。

表2 试点应用前后核心指标对比。

核心指标	应用前	应用后	优化幅度
环保异常漏报率	13.5%	1.8%	降低86.7%
设备故障引发环保问题次数	28次/年	9次/年	降低67.9%
人工运维时长	8.2h/天	3.5h/天	降低57.3%
年均环保运维成本	86.5万元	56.2万元	降低35.0%
VOCs年排放量	1268吨	920吨	降低27.4%

由试点数据可知，大数据赋能的智能运维模式，彻底改善了原油罐区环保运维的被动局面，实现污染精准防控、运维提质增效、成本有效管控，兼顾环保效益、安全效益与经济效益，具备极强的工程推广价值。

6．结论

目前，现有技术在实际应用中仍存在一定短板；极端天气环境会对传感器监测精度造成干扰，导致数据采集精准度出现偏差，复杂多重工况条件下，污染溯源的响应效率仍有提升空间。同时，部分老旧小众设备兼容性较差，难以适配现有数据采集与传输体系。后续将针对性开展技术迭代升级，优化环境抗干扰算法，提升设备复杂工况适应能力；更新换代智能感知终端，夯实数据采集基础；完善多场景适配的数据运算模型。此外，依托数字孪生技术搭建虚拟仿真运维体系，全方位提升系统的智能化与精细化管控能力，稳步推动原油罐区环保运维模式，向无人值守、智慧管控、绿色低碳方向深度升级

[9]

。

References

[1]	董绍华, 张行. 石油及天然气储备库安全保障技术现状及展望. 油气储运. 2018, 37 (03): 241‑247. https://doi.org/10.6047/j.issn.1000‑8241.2018.03.001
[2]	朱喜平. 大型石油储库全寿命周期风险管控一体化平台研发. 油气储运. 2023, 42 (10): 1175‑1183. https://doi.org/10.6047/j.issn.1000‑8241.2023.10.011
[3]	侯磊, 朱淼, 杨兆晶, 等. 某原油库泄漏油品流散数值模拟与分析. 安全与环境学报. 2020, 20 (06): 2116‑2122. https://doi.org/10.13637/j.issn.1009‑6094.2019.1326
[4]	赵志海, 甄永乾, 张健中. 成品油库智能化技术现状及其发展趋势分析. 安全、健康和环境. 2019, 19 (07): 75‑78.
[5]	朱亮. 基于 OP‑FTIR 的罐区 VOCs 排放监测技术. 油气储运. 2020, 39 (06): 704‑708. https://doi.org/10.6047/j.issn.1000‑8241.2020.06.014
[6]	赵杰, 段礼祥, 乔淑君, 等. 储油库 VOCs 多呼吸阀排放的扩散叠加效应分析. 环境工程学报. 2026, 20 (02): 507‑516. https://doi.org/10.12030/j.cjee.202506073
[7]	易高翔, 王如君, 朱天玲, 等. 基于三维 GIS 的油罐区应急管理平台研究与实现. 中国安全生产科学技术. 2013, 9 (05): 122‑127.
[8]	陈福真, 张明广, 王妍, 等. 油气储罐区多米诺事故耦合效应风险分析. 中国安全科学学报. 2017, 27 (10): 111‑116. https://doi.org/10.16265/j.cnki.issn1003‑3033.2017.10.019
[9]	单宝学. 基于数字孪生的油气与化学品储罐区安全运行监测技术研究. 当代化工研究. 2026 (09): 194‑196.
[10]	张杰, 李刚, 黄贤滨, 等. 石化罐区多源监测数据融合与智能预警方法. 石油化工安全环保技术. 2022, 38 (03): 1‑5+70.
[11]	刘骁, 王廷春, 张广文, 等. 浮顶储罐 VOCs 排放在线监测与大数据溯源技术进展. 环境工程. 2021, 49 (08): 1‑8. https://doi.org/10.13205/j.hjgc.202108001
[12]	王洪健, 段礼祥, 张来斌. 基于机器学习的储罐腐蚀状态大数据预警方法. 机械强度. 2021, 43 (04): 839‑845. https://doi.org/10.16579/j.issn.1001‑9669.2021.04.018
[13]	敬一平. AI 赋能下的成品油油库低碳智能化研究与实践. 石油库与加油站. 2025, 34 (04): 1‑6.
[14]	郭伟, 李朝阳, 刘俊娥.智慧罐区环境大数据平台架构与数据治理方法. 环境工程技术学报. 2023, 13 (02): 661‑669. https://doi.org/10.12153/j.issn.1674‑991X.20220347
[15]	HOU L, WU X G, WU Z, et al. Pattern identification and risk prediction of domino effect based on data‑mining methods for accidents occurred in tank farms. Journal of Loss Prevention in the Process Industries. 2018, 55: 247‑256. https://doi.org/10.1016/j.jlp.2018.07.008
[16]	PATEL H, PRAJAPATI D, MAHIDA D, et al. Transforming petroleum downstream sector through big data: a review. Journal of Petroleum Exploration and Production Technology. 2020, 10(07): 2961‑2974. https://doi.org/10.1007/s13202‑020‑00883‑4

Cite This Article

Plain Text BibTeX RIS

APA Style

Liu, H., Ma, C., Tian, H. (2026). Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks. Science Research, 14(6), 439-444. https://doi.org/10.11648/j.sr.20261406.17

Copy | Download

ACS Style

Liu, H.; Ma, C.; Tian, H. Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks. Sci. Res. 2026, 14(6), 439-444. doi: 10.11648/j.sr.20261406.17

Copy | Download

AMA Style

Liu H, Ma C, Tian H. Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks. Sci Res. 2026;14(6):439-444. doi: 10.11648/j.sr.20261406.17

Copy | Download

@article{10.11648/j.sr.20261406.17,
  author = {Haotong Liu and Congzhao Ma and Hongyan Tian},
  title = {Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks},
  journal = {Science Research},
  volume = {14},
  number = {6},
  pages = {439-444},
  doi = {10.11648/j.sr.20261406.17},
  url = {https://doi.org/10.11648/j.sr.20261406.17},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sr.20261406.17},
  abstract = {To address prominent problems in the traditional operation and maintenance of crude oil tank farms, including delayed response of environmental control, low efficiency of fault troubleshooting and insufficient accuracy of pollutant monitoring, this paper constructs an overall framework for intelligent environmental operation and maintenance of crude oil tank farms based on the Internet of Things, edge computing and big data. A terminal-edge-cloud collaborative integrated platform for data acquisition and analysis is established to integrate multi-source monitoring data such as VOCs emissions, site water quality and equipment operating conditions. Combined with data modeling and intelligent algorithms, it realizes accurate traceability of pollution sources, early warning of equipment faults and optimization of operation workflows. Engineering tests prove that the system improves the recognition accuracy of environmental anomalies and operation efficiency, reduces hydrocarbon emissions and energy consumption, and provides technical support for the green, low-carbon, safe and efficient management of petrochemical crude oil tank farms.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks
AU  - Haotong Liu
AU  - Congzhao Ma
AU  - Hongyan Tian
Y1  - 2026/11/10
PY  - 2026
N1  - https://doi.org/10.11648/j.sr.20261406.17
DO  - 10.11648/j.sr.20261406.17
T2  - Science Research
JF  - Science Research
JO  - Science Research
SP  - 439
EP  - 444
PB  - Science Publishing Group
SN  - 2329-0927
UR  - https://doi.org/10.11648/j.sr.20261406.17
AB  - To address prominent problems in the traditional operation and maintenance of crude oil tank farms, including delayed response of environmental control, low efficiency of fault troubleshooting and insufficient accuracy of pollutant monitoring, this paper constructs an overall framework for intelligent environmental operation and maintenance of crude oil tank farms based on the Internet of Things, edge computing and big data. A terminal-edge-cloud collaborative integrated platform for data acquisition and analysis is established to integrate multi-source monitoring data such as VOCs emissions, site water quality and equipment operating conditions. Combined with data modeling and intelligent algorithms, it realizes accurate traceability of pollution sources, early warning of equipment faults and optimization of operation workflows. Engineering tests prove that the system improves the recognition accuracy of environmental anomalies and operation efficiency, reduces hydrocarbon emissions and energy consumption, and provides technical support for the green, low-carbon, safe and efficient management of petrochemical crude oil tank farms.
VL  - 14
IS  - 6
ER  -

Copy | Download

Author Information

Haotong Liu

China National Petroleum Group Safety and Environmental Protection Technology Research Institute, Beijing, China

Contact Email
Congzhao Ma

China National Petroleum Corporation Commercial Reserve Oil Branch, Beijing, China
Hongyan Tian

China National Petroleum Corporation Commercial Reserve Oil Branch, Beijing, China

Download PDF

Submit an Article

Figure 1

Figure 1. 图 1 传统原油罐区环保数据监测架构示意图。
Figure 2

Figure 2. 图 2 整体架构的可视化效果。

Table 1

表1 不同阶段数据利用率对比。
Table 2

表2 试点应用前后核心指标对比。

Plain Text BibTeX RIS

APA Style

Liu, H., Ma, C., Tian, H. (2026). Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks. Science Research, 14(6), 439-444. https://doi.org/10.11648/j.sr.20261406.17

Copy | Download

ACS Style

Liu, H.; Ma, C.; Tian, H. Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks. Sci. Res. 2026, 14(6), 439-444. doi: 10.11648/j.sr.20261406.17

Copy | Download

AMA Style

Liu H, Ma C, Tian H. Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks. Sci Res. 2026;14(6):439-444. doi: 10.11648/j.sr.20261406.17

Copy | Download

@article{10.11648/j.sr.20261406.17,
  author = {Haotong Liu and Congzhao Ma and Hongyan Tian},
  title = {Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks},
  journal = {Science Research},
  volume = {14},
  number = {6},
  pages = {439-444},
  doi = {10.11648/j.sr.20261406.17},
  url = {https://doi.org/10.11648/j.sr.20261406.17},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.sr.20261406.17},
  abstract = {To address prominent problems in the traditional operation and maintenance of crude oil tank farms, including delayed response of environmental control, low efficiency of fault troubleshooting and insufficient accuracy of pollutant monitoring, this paper constructs an overall framework for intelligent environmental operation and maintenance of crude oil tank farms based on the Internet of Things, edge computing and big data. A terminal-edge-cloud collaborative integrated platform for data acquisition and analysis is established to integrate multi-source monitoring data such as VOCs emissions, site water quality and equipment operating conditions. Combined with data modeling and intelligent algorithms, it realizes accurate traceability of pollution sources, early warning of equipment faults and optimization of operation workflows. Engineering tests prove that the system improves the recognition accuracy of environmental anomalies and operation efficiency, reduces hydrocarbon emissions and energy consumption, and provides technical support for the green, low-carbon, safe and efficient management of petrochemical crude oil tank farms.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Study on Using Big Data to Boost Smart and Eco-Friendly Operations for Crude Oil Tanks
AU  - Haotong Liu
AU  - Congzhao Ma
AU  - Hongyan Tian
Y1  - 2026/11/10
PY  - 2026
N1  - https://doi.org/10.11648/j.sr.20261406.17
DO  - 10.11648/j.sr.20261406.17
T2  - Science Research
JF  - Science Research
JO  - Science Research
SP  - 439
EP  - 444
PB  - Science Publishing Group
SN  - 2329-0927
UR  - https://doi.org/10.11648/j.sr.20261406.17
AB  - To address prominent problems in the traditional operation and maintenance of crude oil tank farms, including delayed response of environmental control, low efficiency of fault troubleshooting and insufficient accuracy of pollutant monitoring, this paper constructs an overall framework for intelligent environmental operation and maintenance of crude oil tank farms based on the Internet of Things, edge computing and big data. A terminal-edge-cloud collaborative integrated platform for data acquisition and analysis is established to integrate multi-source monitoring data such as VOCs emissions, site water quality and equipment operating conditions. Combined with data modeling and intelligent algorithms, it realizes accurate traceability of pollution sources, early warning of equipment faults and optimization of operation workflows. Engineering tests prove that the system improves the recognition accuracy of environmental anomalies and operation efficiency, reduces hydrocarbon emissions and energy consumption, and provides technical support for the green, low-carbon, safe and efficient management of petrochemical crude oil tank farms.
VL  - 14
IS  - 6
ER  -

Copy | Download